Speed-optimized, Compact Student Models that Distill Knowledge from a Larger Teacher Model: the UEDIN-CUNI Submission to the WMT 2020 News Translation Task
2020-11-01WMT (EMNLP) 2020Unverified0· sign in to hype
Ulrich Germann, Roman Grundkiewicz, Martin Popel, Radina Dobreva, Nikolay Bogoychev, Kenneth Heafield
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We describe the joint submission of the University of Edinburgh and Charles University, Prague, to the Czech/English track in the WMT 2020 Shared Task on News Translation. Our fast and compact student models distill knowledge from a larger, slower teacher. They are designed to offer a good trade-off between translation quality and inference efficiency. On the WMT 2020 Czech ↔ English test sets, they achieve translation speeds of over 700 whitespace-delimited source words per second on a single CPU thread, thus making neural translation feasible on consumer hardware without a GPU.